Update README.md

README.md

@@ -4,4 +4,16 @@ license: llama3.1
 GGUF [llama.cpp](https://github.com/ggerganov/llama.cpp) quantized version of:
 - Original model: [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
 - Model creator: [Meta](https://huggingface.co/meta-llama)
-- [License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE) 
+- [License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE)
+  
+## Recommended Prompt Format (Llama3)
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+Provide some context and/or instructions to the model.<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+The user’s message goes here<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+AI message goes here<|eot_id|>
+```
+Quant Version: [b3445](https://github.com/ggerganov/llama.cpp/releases/tag/b3445)